Clean Indian code-mixed text before it reaches your LLM.
-
Updated
Mar 20, 2026 - Python
Clean Indian code-mixed text before it reaches your LLM.
Research - The aim of this project is to find the aspect from a given code-mix sentence. The traditional sequence tagging methods are compared with Deep learning methods. The concept of Question and Answering model is used to achieve this task.
Developed a deep learning sequence‑to‑sequence model with an attention mechanism, inspired by neural machine translation, to translate monolingual sequences to code‑mixed sequences and vice versa
Add a description, image, and links to the codemix topic page so that developers can more easily learn about it.
To associate your repository with the codemix topic, visit your repo's landing page and select "manage topics."